From the course: Oracle Cloud Infrastructure Generative AI Professional

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Decoding

Decoding

(soft music) - [Ari] Hello. In the previous lessons we've discussed how large language models compute distributions over vocabulary words and how we can affect those distributions. In this lesson, we'll talk about a few ways we can take these distributions and generate text, otherwise known as decoding. Let's return to the example we've seen a few times thus far. I wrote to the zoo to send me a pet. They sent me a, as we know, the LLM produces a distribution over vocabulary words, and the question we're focused on now is how do we turn this distribution into a word or a sequence of words? Through the course of this discussion, there are a few things that I'd like to drive home. One is that in decoding, or the process of generating text, it happens one word at a time. It's an iterative process. Specifically, we give the model some input text, it produces a distribution over words in its vocabulary. We select one, it gets appended to the input, and then we feed the revised input back…

Contents